Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/anamized/superagenticmcp/agents-mdgit clone --depth 1 https://github.com/ANAMIZED/SuperAgenticMCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/anamized/superagenticmcp/agents-md)<a href="https://agentmods.dev/instructions/anamized/superagenticmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anamized/superagenticmcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
SuperAgenticMCP AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md — SuperAgenticMCP
This file is the contract for any AI coding agent working on this repository.
Layout standard: Server OS
See docs/LAYOUT.md.
What this project is
SuperAgenticMCP is the switchboard for agent swarms: an MCP-native router and multi-agent control plane that racks MCP servers, plans tasks (planner → workers → critic), routes by capability then latency, streams steps to a live board + JSONL log, and files runs into a memory-scope constellation.
A senior engineer with only the source code and README.md must be able to install,
exercise public surfaces, and verify via scripts/verify.sh.
How to run & verify
pip install -e ".[dev]"
make test
bash scripts/verify.sh
MCP: superagenticmcp
CLI: superagenticmcp-cli status
Hero: superagenticmcp.html
WebMCP board: web/board.html
Hard rules for agents
- Never break the verify contract (
scripts/verify.sh). - Fail closed — no silent drops of tool calls or servers.
- Capabilities and allow-lists only — no ambient authority.
- Keep secrets out of source and the hero HTML.
- Simulation belongs only in the browser demo; the real server path must not invent tool results.
- Prefer small, focused changes. Update README.md and AGENTS.md when public surfaces change.
- Do not invent a parallel layout — Server OS is the permanent standard.
- WebMCP is a page front door. Do not replace stdio MCP with it.
Surfaces that must stay working
MCP Server, CLI, SDK import, skills frontmatter, AGENTS.md, scripts/verify.sh, CI, web/board.html.
See docs/WEBMCP.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 47 lines · 417 tokens per session scan A 3b8c0f9e2a5a
SuperAgenticMCP AGENTS.md is an instructions file published in the GitHub repository ANAMIZED/SuperAgenticMCP (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 417 tokens to every session, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
OpenGOS AGENTS.md
AGENTS.md instructions for ANAMIZED/OpenGOS, covering agents.md, what this project is, repository layout, conventions and how to run.
NeedRail AGENTS.md
AGENTS.md instructions for ANAMIZED/NeedRail, covering needrail — agent instructions, what you can do, mcp tools (preferred interface), principles you must respect and example agent flow.
OpenMesha AGENTS.md
AGENTS.md instructions for ANAMIZED/OpenMesha, covering agents.md — openmesha (om), what this project is, how to run & verify, python control plane and another terminal.
LRSI AGENTS.md
AGENTS.md instructions for ANAMIZED/LRSI, covering agents.md — lrsi, what this project is, how to run & verify, foundation (external core) and this repo (outer stack).
Server-OS AGENTS.md
AGENTS.md instructions for ANAMIZED/Server-OS, covering agents.md — server os, what this project is, how to run & verify, hard rules for agents and surfaces that must stay working.
YodMCP AGENTS.md
AGENTS.md instructions for ANAMIZED/YodMCP, covering agents.md — working on yodmcp and new repos.